R: Multi-Class Discriminant Analysis using Binary Predictors

binda page on CRAN.

The "binda" package implements functions for multi-class discriminant analysis using binary predictors, for corresponding variable selection, and for dichotomizing continuous data.

Current Version: 1.0.4

Authors: Sebastian Gibb and Korbinian Strimmer.

Documentation and Installation:

Quick install: enter at the R console: install.packages("binda")

Manual (pdf file) and release history.
Download of binda version 1.0.4 source package.
Archive of previous versions of binda.
Licensed under the GNU GPL version 3 (or any later version).

Methodology Paper:

S. Gibb and K. Strimmer. 2015. Differential protein expression and peak selection in mass spectrometry data by binary discriminant analysis. Bioinformatics 31: 3156-3162. (arXiv:1502.07959)

Case Study: Analysis of Pancreas Cancer Proteomics Data from Fiedler et al. (2009)

The two R scripts below reproduce the complete data analysis including figures as described in Gibb and Strimmer (2015). Please run in this order:

Preprocessing of the raw mass spectrometry data is done using the MALDIquant software.

Misc:

R script for the analysis of the Dorothea data set with binda.
See the sda package for multi-class discriminant analysis with continuous predictors.